Table 3 Area under the receiver operating characteristics (AUROC) for all approaches in both scenarios. In scenario a): ignoring biomarker information (n=1171); Scenario b): only analysing patients which tested C-peptide positive and autoantibody negative (n=96); Scenario c): analyse all patients, adjusting for biomarker results in the model (n=1,171, validated in n=96). CI: credible interval

From: Comparison of Bayesian approaches for developing prediction models in rare disease: application to the identification of patients with Maturity-Onset Diabetes of the Young